Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate this is not read-only and not idempotent, so the description is not solely responsible for safety signaling. It adds useful context that only unpaid sessions can be canceled and paid sessions follow a different path, but it does not describe side effects, reversibility, or required authorization beyond what annotations imply.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with no filler. The primary purpose is front-loaded in the first sentence, and the important exception is placed immediately after.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter tool with an output schema present, the description provides enough context for correct invocation: it defines the target state, the limitation, and points to where refunds are explained. It could be slightly stronger by naming the alternative sibling tool for paid sessions, but the email reference covers the practical gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0% description coverage, and the description does not add any detail about checkout_session_id beyond its existence. The parameter name is self-explanatory, but the description fails to compensate for the lack of schema-level semantic guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Cancel') and a clearly defined resource ('open (unpaid) checkout session'), immediately distinguishing it from sibling tools like create_checkout, complete_checkout, and update_checkout. It also explicitly separates this tool from paid-session handling by stating paid sessions cannot be canceled here.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly states when the tool is appropriate: cancel an open/unpaid checkout session. It also gives an explicit exclusion for paid sessions and points to the patient's complete-details email for refunds, but it does not name a specific sibling tool as the alternative for refunds.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.